Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5021 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8605. Min Act: -0.0002

Data Index: 291518 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8138. Min Act: -0.0002

Data Index: 1180091 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8199. Min Act: -0.0002

Data Index: 612780 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8321. Min Act: -0.0002

Data Index: 666314 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8077. Min Act: -0.0002

Data Index: 401386 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7443. Min Act: -0.0002

Data Index: 1589090 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7764. Min Act: -0.0002

Data Index: 508080 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7748. Min Act: -0.0002

Data Index: 972424 (C4 (Web Text))

Max Activating Token Index: 418

Text #8

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6766. Min Act: -0.0002

Data Index: 767441 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.8131. Min Act: -0.0002

Data Index: 597913 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7346. Min Act: -0.0002

Data Index: 48681 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7097. Min Act: -0.0002

Data Index: 1300112 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7125. Min Act: -0.0002

Data Index: 908292 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7292. Min Act: -0.0002

Data Index: 130826 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6114. Min Act: -0.0002

Data Index: 1533130 (Python Code)

Max Activating Token Index: 328

Text #15

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7230. Min Act: -0.0002

Data Index: 781305 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6638. Min Act: -0.0002

Data Index: 1607651 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6676. Min Act: -0.0002

Data Index: 281531 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.7204. Min Act: -0.0002

Data Index: 830047 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.8605. Min Range: -0.8605

Max Act: 0.6931. Min Act: -0.0002

Data Index: 819512 (C4 (Web Text))

Max Activating Token Index: 435